• 제어로봇시스템학회:학술대회논문집
• /
• 2005.06a
• /
• pp.1983-1989
• /
• 2005

Industrial robots are powerful, extremely accurate multi-jointed systems, but they are heavy and highly rigid because of their mechanical structure and motorization. Therefore, sharing the robot working space with its environment is problematic. A novel pneumatic artificial muscle actuator (PAM actuator) has been regarded during the recent decades as an interesting alternative to hydraulic and electric actuators. Its main advantages are high strength and high power/weight ratio, low cost, compactness, ease of maintenance, cleanliness, readily available and cheap power source, inherent safety and mobility assistance to humans performing tasks. The PAM is undoubtedly the most promising artificial muscle for the actuation of new types of industrial robots such as Rubber Actuator and PAM manipulators. However, some limitations still exist, such as the air compressibility and the lack of damping ability of the actuator bring the dynamic delay of the pressure response and cause the oscillatory motion. In addition, the nonlinearities in the PAM manipulator still limit the controllability. Therefore, it is not easy to realize motion with high accuracy and high speed and with respect to various external inertia loads in order to realize a human-friendly therapy robot To overcome these problems a novel controller, which harmonizes a phase plane switching control method with conventional PID controller and the adaptabilities of neural network, is newly proposed. In order to realize satisfactory control performance a variable damper - Magneto-Rheological Brake (MRB) is equipped to the joint of the manipulator. Superb mixture of conventional PID controller and a phase plane switching control using neural network brings us a novel controller. This proposed controller is appropriate for a kind of plants with nonlinearity uncertainties and disturbances. The experiments were carried out in practical PAM manipulator and the effectiveness of the proposed control algorithm was demonstrated through experiments, which had proved that the stability of the manipulator can be improved greatly in a high gain control by using MRB with phase plane switching control using neural network and without regard for the changes of external inertia loads.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.8
• /
• pp.875-881
• /
• 2014

The redundancy resolution of the seven DOF (Degree of Freedom) upper limb exoskeleton is key to the synchronous motion between a robot and a human user. According to the seven DOF human arm model, positioning and orientating the wrist can be completed by multiple arm configurations that results in the non-unique solution to the inverse kinematics. This paper presents analysis on the kinematic and dynamic aspect of the human arm movement and its effect on the redundancy resolution of the seven DOF human arm model. The redundancy of the arm is expressed mathematically by defining the swivel angle. The final form of swivel angle can be represented as a linear combination of two different swivel angles achieved by optimizing two cost functions based on kinematic and dynamic criteria. The kinematic criterion is to maximize the projection of the longest principal axis of the manipulability ellipsoid of the human arm on the vector connecting the wrist and the virtual target on the head region. The dynamic criterion is to minimize the mechanical work done in the joint space for each of two consecutive points along the task space trajectory. The contribution of each criterion on the redundancy was verified by the post processing of experimental data collected with a motion capture system. Results indicate that the bimodal redundancy resolution approach improved the accuracy of the predicted swivel angle. Statistical testing of the dynamic constraint contribution shows that under moderate speeds and no load, the dynamic component of the human arm is not dominant, and it is enough to resolve the redundancy without dynamic constraint for the realtime application.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.18 no.5
• /
• pp.237-244
• /
• 2018

The Smart Factory level of manufacturing factories of SMEs now lacks a system for grasping the accurate inventory amount associated with inventory movements in managing warehouses at the basic level. Also, it is difficult to manage accurate materials for loss of data due to worker manual work and production method due to experience. In order to solve this problem, in this paper, automatic acquisition of inventory to minimize manual work to grasp workers' Inventory and improve automation is done. In the smart warehouse management system using the IoT-based autonomous mobile module, the autonomous mobile module acquires the data of the inventory storage while moving through the line. In order to grasp the material of the Inventory storage, The Camera module recognizes the name of the inventory storage. And Then, If output matches, the data measured by the sensor is transferred to the server. This data can be processed, saved in a database, and real-time inventory quantity and location can be grasped in a web-based monitoring environment for administrators. The Real-time Automatic Inventory (RAIC) systems is reduce manual tasks and expect the effects of automated inventory management systems.

• Journal of Institute of Control, Robotics and Systems
• /
• v.22 no.3
• /
• pp.241-246
• /
• 2016

Nowadays many people have an interest in facial expression and the behavior of people. These are human-robot interaction (HRI) researchers utilize digital image processing, pattern recognition and machine learning for their studies. Facial feature point detector algorithms are very important for face recognition, gaze tracking, expression, and emotion recognition. In this paper, a cascade facial feature point detector is used for finding facial feature points such as the eyes, nose and mouth. However, the detector has difficulty extracting the feature points from several images, because images have different conditions such as size, color, brightness, etc. Therefore, in this paper, we propose an algorithm using a modified cascade facial feature point detector using a convolutional neural network. The structure of the convolution neural network is based on LeNet-5 of Yann LeCun. For input data of the convolutional neural network, outputs from a cascade facial feature point detector that have color and gray images were used. The images were resized to $32{\times}32$. In addition, the gray images were made into the YUV format. The gray and color images are the basis for the convolution neural network. Then, we classified about 1,200 testing images that show subjects. This research found that the proposed method is more accurate than a cascade facial feature point detector, because the algorithm provides modified results from the cascade facial feature point detector.

• Journal of Institute of Control, Robotics and Systems
• /
• v.21 no.9
• /
• pp.898-902
• /
• 2015

Alternative radio-navigation technologies aim at providing continuous navigation solution even if one cannot use GNSS (Global Navigation Satellite System). In shadowing region such as indoor environment, GNSS signal is no longer available and the alternative navigation system should be used together with GNSS to provide seamless positioning. For soldiers in battlefield where GNSS signal is jammed or in street battle, the alternative navigation system should work without positioning infrastructure. Moreover, the radio-navigation system should have scalability as well as high accuracy performance. This paper presents a TWR (Two-Way-Ranging)-based cooperative positioning system (CPS) that does not require location infrastructure. It is assumed that some members of CPS can obtain GNSS-based position and they are called mobile anchors. Other members unable to receive GNSS signal compute their position using TWR measurements with mobile anchors and neighboring members. Error propagation in CPS is analytically studied in this paper. Error budget for TWR measurements is modeled first. Next, location error propagation in CPS is derived in terms of range errors. To represent the location error propagation in the CPS, Location Error Propagation Indicator (LEPI) is proposed in this paper. Simulation results show that location error of tags in CPS is mainly influenced by the number of hops from anchors to the tag to be positioned as well as the network geometry of CPS.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.7
• /
• pp.637-648
• /
• 2007

This paper presents a sensor fusion method based on indirect Kalman filter(IKF) for error compensation of low-cost inertial sensors and its application to the determination of attitude and position of small flying robots. First, the analysis of the measurement error characteristics to zero input is performed, focusing on the bias due to the temperature variation, to derive a simple nonlinear bias model of low-cost inertial sensors. Moreover, from the experimental results that the coefficients of this bias model possess non-deterministic (stochastic) uncertainties, the bias of low-cost inertial sensors is characterized as consisting of both deterministic and stochastic bias terms. Then, IKF is derived to improve long term stability dominated by the stochastic bias error, fusing low-cost inertial sensor measurements compensated by the deterministic bias model with non-inertial sensor measurement. In addition, in case of using intermittent non-inertial sensor measurements due to the unreliable data link, the upper and lower bounds of the state estimation error covariance matrix of discrete-time IKF are analyzed by solving stochastic algebraic Riccati equation and it is shown that they are dependant on the throughput of the data link and sampling period. To evaluate the performance of proposed method, experimental results of IKF for the attitude determination of a small flying robot are presented in comparison with that of extended Kaman filter which compensates only deterministic bias error model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.20 no.3
• /
• pp.345-355
• /
• 2014

Since the beginning of the 21st century, emergence of innovative technologies in robotic and telepresence surgery has revolutionized minimally access surgery and continually has advanced them till recent years. One of such surgeries is endoscopic surgery, in which endoscope and endoscopic instruments are inserted into the body through small incision or natural openings, surgical operations being carried out by a laparoscopic procedure. Due to a vast amount of developments in this technology, this review article describes only a technological state-of-the arts and trend of endoscopic robots, being further limited to the aspects of key components, their functional requirements and operational procedure in surgery. In particular, it first describes technological limitations in developments of key components and then focuses on the description of the performance required for their functions, which include position control, tracking, navigation, and manipulation of the flexible endoscope body and its end effector as well, and so on. In spite of these rapid developments in functional components, endoscopic surgical robots should be much smaller, less expensive, easier to operate, and should seamlessly integrate emerging technologies for their intelligent vision and dexterous hands not only from the points of the view of surgical, ergonomic but also from safety. We believe that in these respects a medical robotic technology related to endoscopic surgery continues to be revolutionized in the near future, sufficient enough to replace almost all kinds of current endoscopic surgery. This issue remains to be addressed elsewhere in some other review articles.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.4
• /
• pp.334-343
• /
• 2001

Polishing a die that has free-form surfaces is a time-consuming and tedious job, and requires a considerable amount of high-precision skill. Some workers tend to gradually avoid the polishing work because of the poor environment caused by dust and noise. In order to reduce the polishing time and cope with the shortage of skilled workers, a user-friendly automatic polishing system was developed in this research. The polishing system with five degrees of freedom is able to keep the polishing tool normal to the die surface. The polishing system is controlled by a PC-NC controller. To easily operate the developed polishing robot system, this study developed an integrated program in the Windows environment. This program consists of four modules: the polishing module, the graphic simulator, the polishing data generation module, and the teaching module. Also, the automatic teaching system was developed to easily obtain teaching data and it consists of a three dimensional joystick and a proximity sensor. The joystick is used to simultaneously drive the polishing system to an arbitrary orientation and the proximity sensor is used to obtain teaching points precisely. Also, to evaluate the stability of the driving program and the teaching system, polishing experiments of a die of saddle shape were carried out.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.7
• /
• pp.893-898
• /
• 2005

Due to the merits that only a small amount of computation is needed for solutions and stochastic policies can be handled explicitly, the actor-critic algorithm, which is a class of reinforcement learning methods, has recently attracted a lot of interests in the area of artificial intelligence. The actor-critic network composes of tile actor network for selecting control inputs and the critic network for estimating value functions, and in its training stage, the actor and critic networks take the strategy, of changing their parameters adaptively in order to select excellent control inputs and yield accurate approximation for value functions as fast as possible. In this paper, we consider a new actor-critic algorithm employing an RLS(Recursive Least Square) method for critic learning, and policy gradients for actor learning. The applicability of the considered algorithm is illustrated with experiments on the two linked robot arm.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.519-524
• /
• 2009

Recently, reinforcement learning methods have drawn much interests in the area of machine learning. Dominant approaches in researches for the reinforcement learning include the value-function approach, the policy search approach, and the actor-critic approach, among which pertinent to this paper are algorithms studied for problems with continuous states and continuous actions along the line of the actor-critic strategy. In particular, this paper focuses on presenting a method combining the so-called ACFRL(actor-critic fuzzy reinforcement learning), which is an actor-critic type reinforcement learning based on fuzzy theory, together with the RLS-NAC which is based on the RLS filters and natural actor-critic methods. The presented method is applied to a control problem for crawling robots, and some results are reported from comparison of learning performance.